Trust Assessment
lidarr received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 9 findings: 1 critical, 7 high, 1 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Sensitive path access: AI agent config, Sensitive environment variable access: $HOME.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 25/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/rappo/lidarr/SKILL.md:11 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/rappo/lidarr/SKILL.md:8 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/rappo/lidarr/scripts/lidarr.sh:5 | |
| HIGH | Command Injection via Unquoted Variable in URL Path/Query The `artistId` variable, which is derived from user input, is used unquoted in a `curl` command's URL query parameter. This allows for command injection if a malicious user provides input containing shell metacharacters (e.g., `;`, `|`, `&`). The shell will interpret these metacharacters before `curl` executes, leading to arbitrary command execution. URL-encode the `$internalId` variable before inserting it into the URL. For example, use `internalId_encoded=$(echo "$internalId" | jq -sRr @uri)` and then `"$API/album?artistId=$internalId_encoded"`. | LLM | scripts/lidarr.sh:72 | |
| HIGH | Command Injection via Unquoted Variable in URL Path/Query The `albumId` variable, which is derived from user input, is used unquoted in a `curl` command's URL path. This allows for command injection if a malicious user provides input containing shell metacharacters (e.g., `;`, `|`, `&`). The shell will interpret these metacharacters before `curl` executes, leading to arbitrary command execution. URL-encode the `$albumId` variable before inserting it into the URL. For example, use `albumId_encoded=$(echo "$albumId" | jq -sRr @uri)` and then `"$API/album/$albumId_encoded"`. | LLM | scripts/lidarr.sh:97 | |
| HIGH | Command Injection via Unquoted Variable in URL Path/Query The `artistId` variable, which is derived from user input, is used unquoted in a `curl` command's URL path. This allows for command injection if a malicious user provides input containing shell metacharacters (e.g., `;`, `|`, `&`). The shell will interpret these metacharacters before `curl` executes, leading to arbitrary command execution. URL-encode the `$artistId` variable before inserting it into the URL. For example, use `artistId_encoded=$(echo "$artistId" | jq -sRr @uri)` and then `"$API/artist/$artistId_encoded/refresh"`. | LLM | scripts/lidarr.sh:200 | |
| HIGH | Command Injection via Unquoted Variable in URL Path/Query The `artistId` variable, which is derived from user input, is used unquoted in a `curl` command's URL path. This allows for command injection if a malicious user provides input containing shell metacharacters (e.g., `;`, `|`, `&`). The shell will interpret these metacharacters before `curl` executes, leading to arbitrary command execution. URL-encode the `$artistId` variable before inserting it into the URL. For example, use `artistId_encoded=$(echo "$artistId" | jq -sRr @uri)` and then `"$API/artist/$artistId_encoded"`. | LLM | scripts/lidarr.sh:207 | |
| HIGH | Command Injection via Unquoted Variable in URL Path/Query The `artistId` variable, which is derived from user input, is used unquoted in a `curl` command's URL path. This allows for command injection if a malicious user provides input containing shell metacharacters (e.g., `;`, `|`, `&`). The shell will interpret these metacharacters before `curl` executes, leading to arbitrary command execution. URL-encode the `$artistId` variable before inserting it into the URL. For example, use `artistId_encoded=$(echo "$artistId" | jq -sRr @uri)` and then `"$API/artist/$artistId_encoded?deleteFiles=true"`. | LLM | scripts/lidarr.sh:208 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/rappo/lidarr/scripts/lidarr.sh:7 |
Scan History
Embed Code
[](https://skillshield.io/report/7bab6fbf83d9d9c9)
Powered by SkillShield